Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    verbs associated with physical actions or interactions

    oai_token-act-pair · gpt-3.5-turbo

    actions related to games and competition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jan
    -0.91
    iov
    -0.89
    ãĤ¨ãĥ«
    -0.86
    Brazil
    -0.83
    furt
    -0.82
    vier
    -0.81
    OIL
    -0.80
    imar
    -0.80
    Vi
    -0.79
    antha
    -0.79
    POSITIVE LOGITS
     alike
    0.95
     respectively
    0.86
     affair
    0.79
     extraord
    0.77
     drill
    0.72
     striped
    0.72
     MLA
    0.71
     adventure
    0.69
     hereafter
    0.69
     LLP
    0.68
    Act Density 0.126%

    No Known Activations